Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Agent-Engineer-Master/skill-engineer --skill analyze-demandgit clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/agent-engineer-master/skill-engineer/analyze-demand)<a href="https://agentmods.dev/skills/agent-engineer-master/skill-engineer/analyze-demand"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/analyze-demand/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agent-engineer-master/skill-engineer/analyze-demand"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/analyze-demand.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00208 | $0.02949 |
| Opus 5.5 | $0.00083 | $0.01180 |
| Sonnet 5.5 | $0.00042 | $0.00590 |
| Haiku 4.5 | $0.00021 | $0.00295 |
Grade C, and why
analyze-demand scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Built with Agent Engineer Master — get your own production-ready skill: www.agentengineermaster.com/skill-engineer --> How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Demand
For a defined industry, produce a structural demand-side analysis. Output: demand.md that names the JOB the industry's customers are hiring solutions to perform, segments by that job (not demographics), and surfaces substitution risk before it shows in share data.
The discipline: Demand-side analysis is the early-warning system for disruption. Five Forces tells you the structure; profit pools tell you where the money sits today; competitive arena tells you who is winning. Demand analysis tells you whether the question being asked is about to change. JTBD originated in product design; at industry-analysis level it aggregates outcomes across the buyer population to spot cross-category substitution before market-share data moves.
Iron rules:
- Every fact-claim carries a V/C/A/I tag — see
../_shared/provenance-tagging.md. - ≥1 JTBD identified with ALL THREE components (functional / emotional / social) named — even if a component is "minimal" or "absent," state it explicitly. Do not omit.
- ≥2 customer segments defined by the job they hire the product to do, not by demographic or firmographic attributes. "Young urban professionals" or "mid-market SaaS companies" fail this test; "buyers hiring the product to reduce time-to-decision in regulatory submissions" passes.
- ≥1 substitution risk with named substitute candidate (cross-category preferred), explicit switching cost, and stated likelihood. Naming "general competition" or "other vendors" fails.
- Substitution analysis section MUST use the standard heading
## Substitution Risk(exact wording, level-2 heading). Downstream consumers parse by heading; variants fail. - WTP drivers stated per segment — NOT a single price. Drivers explain WHY this segment will or won't pay.
- ≥1 named demand signal with a measurable leading indicator (search trend, channel check, expert-interview language shift, regulatory filing shift, etc.). Lagging metrics like revenue fail.
Process
1. Intake — lock the analysis frame
Confirm: industry slug, geographic scope, B2B / B2C / hybrid, focal value-chain layer (must match the layer used in map-five-forces if running in orchestrator mode), buying-unit definition (individual / household / SMB / enterprise procurement committee). Read references/jtbd-methodology.md and references/customer-segmentation.md. Note any substitution threats already flagged in working/five-forces.md (orchestrator mode) — they are the priority candidates to chase in step 4.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 4.7 KB
- references/customer-segmentation.md 3.9 KB
- references/demand-signals.md 4.1 KB
- references/edge-cases.md 2.5 KB
- references/jtbd-methodology.md 4.8 KB
- references/learnings.md 178 B
- references/substitution-risk.md 5.7 KB
- references/wtp-drivers.md 4.3 KB
- scripts/validate_demand.py 12 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 134 lines · 208 tokens per session scan C 3b65b675589a
analyze-demand is a skill published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 3mo ago), licensed MIT. It adds 208 tokens to every session and 2,949 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
openspec-verify-change
Verify implementation matches OpenSpec change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving. Also use when the user says "openspec verify" or "opsx verify".
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach. Also use when the user says "openspec new change" or "opsx new".
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.